Xinyu Yan
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-damage detection.
The paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a defense mechanism that detects and sanitizes backdoor content planted across multiple workspace interactions.
This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content in local workspace files.
Papers
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu +3 more
The paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a defense mechanism that detects and sanitizes backdoor content planted across mul…